GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Performance Optimization
Presentation
Media
KBLAS: High Performance Level-2 BLAS on Multi-GPU Systems
Abstract:
KBLAS is a library that provides optimized kernels for critical numerical linear algebra operations. It currently provides a subset of standard BLAS kernels. It also extends such kernels to work on multi-GPU systems. KBLAS performance is at least as good as the performance of state-of-the-art libraries, including CUBLAS, MAGMA, and CULA. Some KBLAS kernels score performance speedups that range between 20% and 90%.
 
Topics:
Performance Optimization
Type:
Poster
Event:
GTC Silicon Valley
Year:
2014
Session ID:
P4168
Download:
Share: